Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4987 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2779. Min Act: -0.0000

Data Index: 275479 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1078673 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2264. Min Act: -0.0000

Data Index: 205878 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.2072. Min Act: -0.0000

Data Index: 513381 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1943. Min Act: -0.0000

Data Index: 825008 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1993. Min Act: -0.0000

Data Index: 589178 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1135262 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1779. Min Act: -0.0000

Data Index: 889962 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1808. Min Act: -0.0000

Data Index: 464237 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1732. Min Act: -0.0000

Data Index: 712195 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1787. Min Act: -0.0000

Data Index: 667309 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1729. Min Act: -0.0000

Data Index: 49860 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1749. Min Act: -0.0000

Data Index: 809273 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1796. Min Act: -0.0000

Data Index: 13476 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1172253 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1741. Min Act: -0.0000

Data Index: 170002 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1684. Min Act: -0.0000

Data Index: 242669 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1504. Min Act: -0.0000

Data Index: 867804 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1178325 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.2779. Min Range: -0.2779

Max Act: 0.1460. Min Act: -0.0000

Data Index: 903343 (C4 (Web Text))

Max Activating Token Index: 396